concept
active
concept:task-weightTask weight
Coefficient weighting each task loss in the MTL objective.
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- The space of the model's parameter matrices, where VPD operations take place.
- The paper identifies task difficulty as a key moderator: easy MMLU questions show performative CoT, hard GPQA-Diamond questions show genuine reasoning
- The problem of ensuring all tasks in MTL perform well, avoiding dominance by some tasks.
- Novel task asking which of two sentences received a stronger injection, using matched-pairs design to control for positional bias
- Editing network weights to test predictions about circuit function; proposed as falsifiability test for circuit claims
- Baseline MTL approach minimizing sum of task losses with equal weights; suffers from task balancing
- Logit weight contributions from a feature that arise due to superposition with other features, not from the feature's own causal role
- A formal context with a suggestive interpretation used in conceptual scaling.